add regular expression while deciphering encrypting data

_unittests/ut_filehelper/test_backup_file.py

@@ -140,5 +140,10 @@ def test_backup_file(self):
             c1 = f.read()
         self.assertEqual(c1, c2)
 
+        detemp = os.path.join(temp, "retrieved")
+        s = enc.retrieve_all(detemp, regex=".*[.]py")
+        assert len(s) > 0
+
+
 if __name__ == "__main__":
     unittest.main()

src/pyquickhelper/cli/encryption_cli.py

@@ -39,18 +39,26 @@ def get_parser(encrypt):
             '--map',
             default="crypt_map.txt",
             help='mapping between raw files and crypted files')
+    else:
+        parser.add_argument(
+            '-r',
+            '--regex',
+            default="",
+            help='the script can retrieve only a subpart of the data defined by a regular expression')
+
     return parser
 
 
 def do_main(source, dest, password, encrypt,
-            crypt_file, crypt_map, fLOG=None):
+            crypt_file, crypt_map, regex=None, fLOG=None):
     """
     Encrypt or decrypt of folder, see @see cl EncryptedBackup.
 
     @param      source      source of files to encrypt or decrypt
     @param      dest        destination
     @param      password    password
     @param      encrypt     boolean, True to encrypt
+    @param      regex       regular expression to filter in files to retrieve
     @param      fLOG        logging function
     """
     if not os.path.exists(source):
@@ -95,7 +103,7 @@ def do_main(source, dest, password, encrypt,
             fLOG=fLOG)
 
         print("start restoration")
-        enc.retrieve_all(source)
+        enc.retrieve_all(source, regex=regex)
 
 
 def encrypt():
@@ -111,8 +119,7 @@ def encrypt():
 
     if args is not None:
         do_main(source=args.source, dest=args.dest, password=args.password,
-                encrypt=True, crypt_file=args.status, crypt_map=args.map,
-                fLOG=print)
+                encrypt=True, crypt_file=args.status, crypt_map=args.map, fLOG=print)
 
 
 def decrypt():
@@ -129,6 +136,7 @@ def decrypt():
     if args is not None:
         do_main(source=args.dest, dest=args.source, password=args.password,
                 encrypt=False, crypt_file=None, crypt_map=None,
+                regex=args.regex if args.regex else None,
                 fLOG=print)
 
 if __name__ == "__main__":

src/pyquickhelper/filehelper/encrypted_backup.py

@@ -400,24 +400,34 @@ def retrieve(self, path, filename=None, root=None):
                         byt.write(data)
                     return byt.getvalue()
 
-    def retrieve_all(self, dest):
+    def retrieve_all(self, dest, regex=None):
         """
         retrieve all backuped files
 
         @param      dest        destination
+        @param      regex       retrieve a subset matching the regular expression
         @return                 list of restored files
         """
+        rema = re.compile(regex) if regex else None
+
+        def match(na):
+            if rema:
+                return rema.search(na)
+            else:
+                return True
+
         self.fLOG("load mapping")
         self.load_mapping()
         self.fLOG("number of files", len(self.Mapping))
         done = []
         for k, v in sorted(self.Mapping.items()):
             name = self.retrieve(k, root=dest)
-            size = os.stat(name).st_size
-            self.fLOG("[download % 8d bytes name=%s -- fullname=%s -- to=%s]" % (
-                size,
-                os.path.split(name)[-1],
-                dest,
-                os.path.dirname(name)))
-            done.append(name)
+            if match(name):
+                size = os.stat(name).st_size
+                self.fLOG("[download % 8d bytes name=%s -- fullname=%s -- to=%s]" % (
+                    size,
+                    os.path.split(name)[-1],
+                    dest,
+                    os.path.dirname(name)))
+                done.append(name)
         return done

src/pyquickhelper/loghelper/repositories/pygit_helper.py

@@ -83,12 +83,13 @@ def __str__(self):
         """
         return self.name
 
+
 def get_cmd_git():
     """
     get the command line used to run git
-    
+
     @return     string
-    
+
     .. versionadded:: 1.3
     """
     if sys.platform.startswith("win32"):
@@ -219,7 +220,7 @@ def get_repo_log(path=None, file_detail=False, commandline=True):
     else:
         cmd = get_cmd_git()
         cmd += ' log --pretty=format:"<logentry revision=\\"%h\\"><author>%an</author><date>%ci</date><msg>%s</msg><hash>%H</hash></logentry>" ' + \
-                path
+            path
 
         enc = sys.stdout.encoding if sys.version_info[
             0] != 2 and sys.stdout is not None else "utf8"